About the role
About the Team
The Preparedness team is an important part of the Safety Systems https://openai.com/safety/safety-systems org at OpenAI, and is guided by OpenAI’s Preparedness Framework https://openai.com/index/updating-our-preparedness-framework/.
Frontier AI models have the potential to benefit all of humanity, but also pose increasingly severe risks. To ensure that AI promotes positive change, the Preparedness team helps us prepare for the development of increasingly capable frontier AI models. This team is tasked with identifying, tracking, and preparing for catastrophic risks related to frontier AI models.
The mission of the Preparedness team is to
- Closely monitor and predict the evolving capabilities of frontier AI systems, with an eye towards misuse risks whose impact could be catastrophic to our society
- Ensure we have concrete procedures, infrastructure and partnerships to mitigate these risks and to safely handle the development of powerful AI systems
Preparedness tightly connects capability assessment, evaluations, and internal red teaming, and mitigations for frontier models, as well as overall coordination on AGI preparedness. This is fast paced, exciting work that has far reaching importance for the company and for society.
About the Role
We’re hiring a Data Scientist to help build, evaluate, and continuously improve mitigations that prevent extreme harms from AI systems. This role is for an experienced, highly autonomous individual contributor who can take ambiguous problem statements, structure rigorous analyses, and translate findings into actionable product and policy changes.
This position goes beyond “running evals.” You’ll help create mitigation intelligence and monitoring systems that enable OpenAI to detect issues early, measure effectiveness over time, and reduce both over-blocking (unnecessary friction) and under-blocking (missed harm).
WHAT YOU’LL DO
- Evaluate and improve mitigation systems, including classifiers and detection pipelines across domains (e.g., biosecurity, cybersecurity, and emerging risk areas).
- Diagnose false positives and false negatives with deep error analysis, root cause investigation, and clear recommendations for mitigation adjustments.
- Build monitoring and measurement frameworks to track mitigation effectiveness over time and across user segments and use cases.
- Identify trends in over-blocking vs. under-blocking, quantify customer impact, and propose prioritized interventions.